{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2KIQ3J5544FAMTAET677CD2AI3","short_pith_number":"pith:2KIQ3J55","canonical_record":{"source":{"id":"2605.25527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T07:33:56Z","cross_cats_sorted":["cs.CE"],"title_canon_sha256":"df560f54a1b499521b831c3b28e5579ca86a83d1554fd46cc25cc273d90a2276","abstract_canon_sha256":"771304a0f8a15493c9baf6ae9d114f9bc32af5e03c63ff4a69d3322f43366559"},"schema_version":"1.0"},"canonical_sha256":"d2910da7bde70a064c049fbff10f4046e1ee3f2b056e4e7ef687e60b5f3b386f","source":{"kind":"arxiv","id":"2605.25527","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25527","created_at":"2026-05-26T02:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25527v1","created_at":"2026-05-26T02:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25527","created_at":"2026-05-26T02:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"2KIQ3J5544FA","created_at":"2026-05-26T02:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"2KIQ3J5544FAMTAE","created_at":"2026-05-26T02:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"2KIQ3J55","created_at":"2026-05-26T02:04:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2KIQ3J5544FAMTAET677CD2AI3","target":"record","payload":{"canonical_record":{"source":{"id":"2605.25527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T07:33:56Z","cross_cats_sorted":["cs.CE"],"title_canon_sha256":"df560f54a1b499521b831c3b28e5579ca86a83d1554fd46cc25cc273d90a2276","abstract_canon_sha256":"771304a0f8a15493c9baf6ae9d114f9bc32af5e03c63ff4a69d3322f43366559"},"schema_version":"1.0"},"canonical_sha256":"d2910da7bde70a064c049fbff10f4046e1ee3f2b056e4e7ef687e60b5f3b386f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:41.065839Z","signature_b64":"Rf9Vil1H+BsPsPvyJRVEoNxyqEgkkYG2G//XFhpg98sf3f9aEqrbA+A9QxuwYeuGWvdYVgW+TjS36tuWtOOaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2910da7bde70a064c049fbff10f4046e1ee3f2b056e4e7ef687e60b5f3b386f","last_reissued_at":"2026-05-26T02:04:41.064940Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:41.064940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.25527","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:04:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qn/aKCW4GZT+O1HzCY5KArh7NFSEnAPWzV5sKHhw5aHzYdJ641gtu1OmLyzve6PZFPfmjATwhc2pNov6fr3nCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T01:59:53.363775Z"},"content_sha256":"704e581b4298b06baf01fc9e2dc66c7f6ad1114fd5e91a43daebd5dc413514f3","schema_version":"1.0","event_id":"sha256:704e581b4298b06baf01fc9e2dc66c7f6ad1114fd5e91a43daebd5dc413514f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2KIQ3J5544FAMTAET677CD2AI3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeepSeekMath Meets Order Book: Group-Aware Policy Optimization for High-Frequency Directional Trading","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE"],"primary_cat":"cs.LG","authors_text":"Sayak Charabarty, Souradip Pal","submitted_at":"2026-05-25T07:33:56Z","abstract_excerpt":"This paper studies reinforcement learning for high-frequency trading on limit order books by pairing an Order-Flow-based state model with policy-gradient methods. Instead of value-based RL techniques like tabular Q-learning, our approach deploys policy-based methods like vanilla PPO and DeepSeekMath-inspired variants like GRPO and GSPO, that use group-normalized updates and downside-aware shaping. On backtests with financial assets AMZN, AAPL, and GOOG under a simplified backtesting setup based on spread-scaled rewards, these new policies improve net average PnL, profitability, and drawdown ov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25527","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.25527/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T02:04:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OUJ0XaE4Xc8EEWi2sWGGceiUreosQYXDFQsZFzUuLQCDvBEv1AbaZxXU4aewhLQfNNzl7ZdducpGYZoa4Es5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T01:59:53.364192Z"},"content_sha256":"4bb003e85d2ba4ddf99097040c6cee4571fa3dd2893c2860c0bf1a601c5b9ef7","schema_version":"1.0","event_id":"sha256:4bb003e85d2ba4ddf99097040c6cee4571fa3dd2893c2860c0bf1a601c5b9ef7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2KIQ3J5544FAMTAET677CD2AI3/bundle.json","state_url":"https://pith.science/pith/2KIQ3J5544FAMTAET677CD2AI3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2KIQ3J5544FAMTAET677CD2AI3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-02T01:59:53Z","links":{"resolver":"https://pith.science/pith/2KIQ3J5544FAMTAET677CD2AI3","bundle":"https://pith.science/pith/2KIQ3J5544FAMTAET677CD2AI3/bundle.json","state":"https://pith.science/pith/2KIQ3J5544FAMTAET677CD2AI3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2KIQ3J5544FAMTAET677CD2AI3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2KIQ3J5544FAMTAET677CD2AI3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"771304a0f8a15493c9baf6ae9d114f9bc32af5e03c63ff4a69d3322f43366559","cross_cats_sorted":["cs.CE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T07:33:56Z","title_canon_sha256":"df560f54a1b499521b831c3b28e5579ca86a83d1554fd46cc25cc273d90a2276"},"schema_version":"1.0","source":{"id":"2605.25527","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25527","created_at":"2026-05-26T02:04:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25527v1","created_at":"2026-05-26T02:04:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25527","created_at":"2026-05-26T02:04:41Z"},{"alias_kind":"pith_short_12","alias_value":"2KIQ3J5544FA","created_at":"2026-05-26T02:04:41Z"},{"alias_kind":"pith_short_16","alias_value":"2KIQ3J5544FAMTAE","created_at":"2026-05-26T02:04:41Z"},{"alias_kind":"pith_short_8","alias_value":"2KIQ3J55","created_at":"2026-05-26T02:04:41Z"}],"graph_snapshots":[{"event_id":"sha256:4bb003e85d2ba4ddf99097040c6cee4571fa3dd2893c2860c0bf1a601c5b9ef7","target":"graph","created_at":"2026-05-26T02:04:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.25527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies reinforcement learning for high-frequency trading on limit order books by pairing an Order-Flow-based state model with policy-gradient methods. Instead of value-based RL techniques like tabular Q-learning, our approach deploys policy-based methods like vanilla PPO and DeepSeekMath-inspired variants like GRPO and GSPO, that use group-normalized updates and downside-aware shaping. On backtests with financial assets AMZN, AAPL, and GOOG under a simplified backtesting setup based on spread-scaled rewards, these new policies improve net average PnL, profitability, and drawdown ov","authors_text":"Sayak Charabarty, Souradip Pal","cross_cats":["cs.CE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T07:33:56Z","title":"DeepSeekMath Meets Order Book: Group-Aware Policy Optimization for High-Frequency Directional Trading"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25527","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:704e581b4298b06baf01fc9e2dc66c7f6ad1114fd5e91a43daebd5dc413514f3","target":"record","created_at":"2026-05-26T02:04:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"771304a0f8a15493c9baf6ae9d114f9bc32af5e03c63ff4a69d3322f43366559","cross_cats_sorted":["cs.CE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T07:33:56Z","title_canon_sha256":"df560f54a1b499521b831c3b28e5579ca86a83d1554fd46cc25cc273d90a2276"},"schema_version":"1.0","source":{"id":"2605.25527","kind":"arxiv","version":1}},"canonical_sha256":"d2910da7bde70a064c049fbff10f4046e1ee3f2b056e4e7ef687e60b5f3b386f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2910da7bde70a064c049fbff10f4046e1ee3f2b056e4e7ef687e60b5f3b386f","first_computed_at":"2026-05-26T02:04:41.064940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:41.064940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rf9Vil1H+BsPsPvyJRVEoNxyqEgkkYG2G//XFhpg98sf3f9aEqrbA+A9QxuwYeuGWvdYVgW+TjS36tuWtOOaBg==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:41.065839Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25527","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:704e581b4298b06baf01fc9e2dc66c7f6ad1114fd5e91a43daebd5dc413514f3","sha256:4bb003e85d2ba4ddf99097040c6cee4571fa3dd2893c2860c0bf1a601c5b9ef7"],"state_sha256":"5fa7e594c3bf579084a8308d63216f8fff787587df078a356a1adcf8e6bd318b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HnhvlEk4Gyz53Zw7et4LODywbZMYr3e852Qwik51gB19DOX2gH82mxo2j003aS2pTWvPa0Y5CSsoIhxool18Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T01:59:53.366293Z","bundle_sha256":"70f44eb2eddf421ffb729cab57867836e1ff14c8eadf7d7b4cfa728addfaa7e8"}}